Raw material quality analysis and health food evaluation method based on multi-dimensional data fusion

Abstract

The invention relates to the technical field of health food evaluation, and discloses a multi-dimensional data fusion-based raw material quality analysis and health food evaluation method, the raw material quality analysis method comprises the following steps: carrying out component analysis on an extract of a target raw material, and determining a plurality of main components contained in the target raw material; performing quality analysis on each main component according to a preset quality index to obtain a quality score of each main component; and performing summation based on the quality scores of the main components to obtain a quality analysis result of the target raw material. According to the method, the contribution value of each main component to the overall efficiency of the raw material is accurately quantified, the quality score of each main component in the target raw material is determined, a raw material comprehensive scoring system covering the activity, content distribution and clinical value of the components is formed through a standardized calculation process, and the limitation of a traditional single index is broken through through multi-dimensional data fusion. The contribution and synergistic effect of each component are accurately quantified, and the evaluation accuracy is improved by combining content and activity scores.

Description

Technical Field

[0001] This invention relates to the field of health food evaluation technology, specifically to a method for raw material quality analysis and health food evaluation based on multidimensional data fusion. Background Technology

[0002] The current quality evaluation system for traditional health food raw material extracts has significant limitations. It relies excessively on single indicators (such as the content of key active ingredients) for quality judgment, failing to comprehensively reflect the overall quality and actual efficacy of the raw materials. This evaluation method ignores the complexity of the synergistic effects of multiple components in the raw materials, as well as the differences in the content of main components due to variations in origin and extraction processes, easily leading to misjudgments of product efficacy. Furthermore, in the formulation design stage of health food products, most products are still limited to mechanically applying traditional prescription compatibility models, failing to fully integrate modern scientific research findings. They lack systematic research on the interactions of formulation components, dosage optimization, and target points, resulting in deficiencies in product innovation, functionality, and scientific rigor, making it difficult to meet the diverse needs of modern consumers for precise nutrition and health intervention. Summary of the Invention

[0003] In view of this, the present invention provides a method for raw material quality analysis and health food evaluation based on multidimensional data fusion, in order to solve the problem that the raw material quality analysis is singular and cannot comprehensively and accurately evaluate health foods.

[0004] In a first aspect, the present invention provides a raw material quality analysis method based on multidimensional data fusion, the method comprising:

[0005] Component analysis was performed on the extract of the target raw material to identify several major components contained in the target raw material;

[0006] According to the preset quality indicators, the quality of each major component is analyzed to obtain the quality score of each major component;

[0007] The quality analysis results of the target raw material are obtained by summing the quality scores of each major component.

[0008] The raw material quality analysis method based on multidimensional data fusion provided by this invention accurately quantifies the contribution value of each major component to the overall efficacy of the raw material, determines the quality score of each major component in the target raw material, and forms a comprehensive raw material scoring system covering component activity, content distribution and clinical value through standardized calculation process. By integrating multidimensional data, it breaks through the limitations of traditional single indicators, accurately quantifies the contribution and synergistic effect of each component, and improves the accuracy of assessment by combining content and activity scores.

[0009] In one optional implementation, the preset quality indicators include: molecular docking binding energy, bioavailability, drug-likeness, and validation from known literature. Based on these preset quality indicators, quality analysis is performed on each major component to obtain a quality score for each major component, including:

[0010] The binding energy of each major component to the target protein is calculated based on molecular docking technology, and the binding energy score corresponding to the binding energy value is determined according to the binding energy scoring standard.

[0011] The bioavailability and drug-likeness of each major component were retrieved through the pharmacology database and analysis platform of traditional Chinese medicine. The bioavailability score was obtained by scoring according to the corresponding bioavailability scoring standard, and the drug-likeness score was obtained by scoring according to the corresponding drug-likeness scoring standard.

[0012] Based on literature retrieval from a pre-defined database, scores are assigned according to whether there is literature record, whether there is in vivo experimental verification, and whether there is in vitro experimental verification, to obtain a known literature verification score.

[0013] The quality score of each major component is calculated using a weighted summation method based on its binding energy score, bioavailability score, drug-likeness score, known literature validation score, and corresponding preset weights.

[0014] The raw material quality analysis method based on multidimensional data fusion provided by this invention deeply integrates four core information units: raw material component spectrum analysis, molecular simulation binding energy prediction, bioactivity characteristic parameters, and experimental literature evidence. By constructing a systematic quantitative model, it accurately calculates the contribution weight of each active ingredient in the raw material to the overall efficacy, and comprehensively reveals the quality characteristics, efficacy potential, and synergistic mechanism between components of the raw material, providing scientific guidance for raw material screening and formulation optimization.

[0015] In one optional implementation, the binding energy between each major component and the target protein is calculated based on molecular docking technology, and a binding energy score corresponding to the binding energy value is determined according to a binding energy scoring standard, including:

[0016] Obtain the functions of the target product, and screen multiple functional target proteins based on the functions of the target product as target target proteins;

[0017] Using molecular docking software, each major component was docked with the target protein one by one to obtain the binding energy between each major component and the target protein.

[0018] Based on the scoring criteria, the range of binding energy values ​​corresponding to different scores is determined. According to the range of binding energy values ​​to which the binding energy of each major component belongs to the target protein, the binding energy score of each major component is determined.

[0019] The raw material quality analysis method based on multidimensional data fusion provided by this invention ensures the specificity of the assessment by matching target proteins with target functions. It calculates binding energy and determines scores based on molecular docking technology, breaking through the limitations of traditional single-index evaluation. It can accurately predict the affinity and interaction strength between components and targets, quantify the contribution weight of each component to efficacy, and comprehensively reveal the synergistic mechanism between components. It provides a scientific quantitative basis for raw material screening and formulation optimization, improves the accuracy and scientific nature of health food research and development, effectively avoids efficacy misjudgments caused by single indicators, and promotes the industry towards a data-driven precision research and development model.

[0020] In one optional implementation, a quality score for each major component is calculated using a weighted summation method based on its binding energy score, bioavailability score, drug-likeness score, known literature validation score, and corresponding preset weights. This includes:

[0021] The binding energy score, bioavailability score, drug-likeness score, and known literature validation score were standardized to obtain multiple scores with the same scoring criteria.

[0022] The quality score of the main component is calculated by using a weighted summation method based on multiple scores with the same scoring criteria and their corresponding preset weights.

[0023] This invention provides a raw material quality analysis method based on multidimensional data fusion. By standardizing the scores of each dimension and combining them with weighted summation to calculate the quality score, this method overcomes the limitations of traditional single-indicator evaluation and achieves quantitative fusion of multidimensional data. This method eliminates dimensional differences between different scoring systems, making heterogeneous data such as binding energy and bioavailability comparable. Through weight allocation, it accurately reflects the contribution ratio of each indicator to the activity of the components. It can comprehensively reveal the synergistic effects between components, avoid misjudgments of efficacy due to single-dimensional bias, and provide a scientific quantitative basis for raw material quality control and formulation optimization.

[0024] Secondly, this invention provides a method for evaluating health food based on multidimensional data fusion, the method comprising:

[0025] To identify the target function of the target health food and to screen for efficacy target proteins based on the target function;

[0026] Obtain multiple test formulations of the target health food, determine multiple main raw materials and their corresponding content percentages in each test formulation, and determine the quality score of each main raw material based on the raw material quality analysis method based on multidimensional data fusion in any of the first aspects.

[0027] The comprehensive efficacy index of the test formulation is obtained by coupling calculation based on the quality scores and corresponding content percentages of the main raw materials in each test formulation.

[0028] In one alternative implementation, the method further includes:

[0029] Based on the target function, the formulation with the best overall performance is selected from all the formulations under test according to the summative efficacy index of each formulation.

[0030] The health food evaluation method based on multidimensional data fusion provided by this invention breaks through the limitations of single-indicator evaluation models by integrating multidimensional data. It achieves a scientific and quantitative evaluation of the entire chain from raw material screening to formulation optimization. Based on the target function, it accurately matches target proteins to ensure the targeted nature of the evaluation. By combining the raw material quality score and content ratio for coupled calculation, it quantifies the synergistic effect of multiple components. By integrating multi-dimensional data such as component activity, content distribution, and clinical evidence, it forms a comprehensive evaluation system covering the quality and efficacy potential of raw materials. This provides a data-driven decision-making basis for formulation optimization, effectively improving the accuracy and scientific nature of health food research and development, and promoting the industry's upgrade to an intelligent evaluation model based on multidimensional data fusion.

[0031] Thirdly, the present invention provides a raw material quality analysis device based on multidimensional data fusion, the device comprising:

[0032] The component analysis module is used to perform component analysis on the extract of the target raw material to determine the multiple main components contained in the target raw material;

[0033] The main component scoring module is used to perform quality analysis on each main component according to preset quality indicators and obtain the quality score of each main component.

[0034] The raw material quality analysis module is used to sum the quality scores of each major component to obtain the quality analysis results of the target raw material.

[0035] Fourthly, the present invention provides a health food evaluation device based on multidimensional data fusion, the device comprising:

[0036] The target protein identification module is used to obtain the target function of the target health food and screen efficacy target proteins based on the target function.

[0037] The raw material scoring module is used to perform principal component analysis on the target health food, determine the multiple main raw materials that make up the target health food and their corresponding content proportions, and determine the quality score of each main raw material according to the raw material quality analysis method based on multidimensional data fusion in any of the first aspects.

[0038] The functional evaluation module is used to perform coupled calculations based on the quality scores and corresponding content percentages of each main raw material to obtain the comprehensive efficacy index of the target health food. The comprehensive efficacy index is used to evaluate the function of the health food.

[0039] Fifthly, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the computer instructions to perform the raw material quality analysis method based on multidimensional data fusion of the first aspect or any corresponding embodiment, and the health food evaluation method based on multidimensional data fusion of the second aspect or any corresponding embodiment.

[0040] In a sixth aspect, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the raw material quality analysis method based on multidimensional data fusion of the first aspect or any corresponding embodiment thereof, and the health food evaluation method based on multidimensional data fusion of the second aspect or any corresponding embodiment thereof. Attached Figure Description

[0041] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0042] Figure 1 This is a flowchart illustrating a raw material quality analysis method based on multidimensional data fusion according to an embodiment of the present invention.

[0043] Figure 2 This is a flowchart illustrating another raw material quality analysis method based on multidimensional data fusion according to an embodiment of the present invention;

[0044] Figure 3 This is a flowchart illustrating the health food evaluation method based on multidimensional data fusion according to an embodiment of the present invention;

[0045] Figure 4 This is a structural block diagram of a raw material quality analysis device based on multidimensional data fusion according to an embodiment of the present invention;

[0046] Figure 5 This is a structural block diagram of a health food evaluation device based on multidimensional data fusion according to an embodiment of the present invention;

[0047] Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0048] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0049] This invention provides a method for raw material quality analysis and health food evaluation based on multidimensional data fusion. By using multidimensional data fusion, the method accurately quantifies the contribution value of each major component to the overall efficacy of the raw material, so as to achieve the effect of comprehensive scoring of raw materials from multiple aspects such as component activity, content distribution and clinical value.

[0050] According to an embodiment of the present invention, a method for raw material quality analysis based on multidimensional data fusion is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0051] This embodiment provides a raw material quality analysis method based on multidimensional data fusion, which can be used in the aforementioned computer system. Figure 1 This is a flowchart of a raw material quality analysis method based on multidimensional data fusion according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0052] Step S101: Perform component analysis on the extract of the target raw material to identify the multiple main components contained in the target raw material.

[0053] Specifically, target raw materials typically refer to the initial substances used to prepare bioactive substances, drugs, or functional products. Their composition is complex and contains multiple bioactive molecules. To facilitate accurate analysis of the components in the raw materials, component analysis is usually performed on the extracts to identify several major components. Component analysis methods are mature existing technologies and will not be elaborated here. Advanced analytical techniques such as High Performance Liquid Chromatography (HPLC) and Gas Chromatography-Mass Spectrometry (GC-MS) can be used to comprehensively and systematically analyze the components of the raw material extracts, accurately determining the content of their major components. Active substances with a high content and potentially key functions of the raw material can be selected as major components. There can be one or more major components. For example, in ginseng extract, the content of ginsenosides such as Rg1 and Rb1 is often higher than other trace components, and they can be considered major components of ginseng. This is just an example and is not a limitation.

[0054] Step S102: According to the preset quality indicators, perform quality analysis on each major component to obtain the quality score of each major component.

[0055] Specifically, for each major component of the raw material, a quality analysis is performed according to preset quality indicators, as shown in Table 1, which shows the preset quality indicators and scoring range. Each major component is scored according to the preset quality indicators in Table 1. The weight coefficients corresponding to each preset quality indicator can be determined based on expert experience. This is just an example and is not a limitation. For each major component, a weighted sum is performed based on its preset quality indicator score and the corresponding weight coefficient to obtain the quality score of each major component.

[0056] Table 1

[0057] Preset quality indicators Weighting coefficient Rating range Molecular docking binding energy 40％ 1-5 points Bioavailability 30％ 1-5 points Drug-like properties 15％ 1-5 points Validation of known literature 15％ 0-2 points

[0058] Step S103: Sum the quality scores of each major component to obtain the quality analysis results of the target raw material.

[0059] Specifically, for the quality analysis results of the target raw material, the quality scores of multiple main components constituting the target raw material are summed to obtain the total score as the quality analysis result of the target raw material. For example, if the quality score of ginsenoside Rg1 in ginseng extract is 4.4 points and the quality score of ginsenoside Rb1 is 3.4 points, then the quality analysis result of ginseng extract is 7.8 points. This is just an example and is not a limitation.

[0060] The raw material quality analysis method based on multidimensional data fusion provided in this embodiment accurately quantifies the contribution of each major component to the overall efficacy of the raw material, determines the quality score of each major component in the target raw material, and forms a comprehensive raw material scoring system covering component activity, content distribution and clinical value through standardized calculation process. By integrating multidimensional data, it breaks through the limitations of traditional single indicators, accurately quantifies the contribution and synergistic effect of each component, and improves the accuracy of assessment by combining content and activity scores.

[0061] This embodiment provides a raw material quality analysis method based on multidimensional data fusion, which can be used in the aforementioned computer system. Figure 2 This is a flowchart of a raw material quality analysis method based on multidimensional data fusion according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps:

[0062] Step S201 involves performing component analysis on the extract of the target raw material to identify the multiple main components contained within it. For details, please refer to [link to relevant documentation]. Figure 1 Step S101 of the illustrated embodiment will not be described again here.

[0063] Step S202: According to the preset quality indicators, perform quality analysis on each major component to obtain the quality score of each major component.

[0064] Specifically, the preset quality indicators include: molecular docking binding energy, bioavailability, drug-likeness, and verification from known literature. Step S202 includes:

[0065] Step S2021: Calculate the binding energy between each major component and the target protein based on molecular docking technology, and determine the binding energy score corresponding to the binding energy value according to the binding energy scoring standard.

[0066] Specifically, the chemical structures of the main components in the raw materials were input into a chemical structure drawing software (ChemBio3DUltra 21.0.0.28) to minimize energy, and the minimum root mean square gradient (RMSGradient) was adjusted to 0.01. The optimized chemical structure was saved in pdb format. Then, the structure of the target protein was imported into a molecular and protein visualization software (Pymol 2.3.0) and optimized. Next, the optimized small molecules and receptor proteins were processed in a visualization program (AutodockTools-1.5.6), and the rotatable bonds were set. Finally, the structure was saved in "pdbqt" format. Based on molecular docking software (AutoDock Vina 1.1.2), the small molecule compounds were precisely docked with the target proteins one by one to obtain the binding energy data of the active ingredient and the target protein. Finally, the binding energy data was quantitatively scored strictly according to a pre-set binding energy scoring standard.

[0067] In some optional implementations, step S2021 above includes:

[0068] Step a1: Obtain the functions of the target product, and screen multiple functional target proteins based on the functions of the target product as target target proteins.

[0069] Specifically, based on the health benefits that the target product intends to claim, efficacy target proteins that match its function are selected as target target proteins through literature retrieval and other means. There are generally multiple efficacy target proteins.

[0070] Step a2: Using molecular docking software, each major component is docked with the target protein one by one to obtain the binding energy between each major component and the target protein.

[0071] Specifically, molecular docking software is used to perform molecular simulation docking technology to analyze the main components of the screened raw materials one by one with the target protein, and to calculate the corresponding binding energy values. For example, a raw material includes three main components: component A, component B, and component C. The target targets determined based on the function of the target product include protein α, protein β, and protein γ. Therefore, it is necessary to calculate the binding energies of component A with protein α, component A with protein β, component A with protein γ, component B with protein α, component B with protein β, component B with protein γ, component C with protein α, component C with protein β, and component C with protein γ. The binding energies of component A with protein α, component A with protein β, and component A with protein γ should be scored according to Table 2, and the sum of these scores should be the total binding energy score for component A. Similarly, the binding energies of component B with protein α, component B with protein β, and component B with protein γ should be scored according to Table 2, and the sum of these scores should be the total binding energy score for component B. The binding energies of component C with protein α, component C with protein β, and component C with protein γ should be scored according to Table 2, and the sum of these scores should be the total binding energy score for component C. This is just an example and is not a limitation.

[0072] Step a3: Determine the range of binding energy values ​​corresponding to different scores based on the scoring criteria, and determine the binding energy score of each major component according to the range of binding energy values ​​to which the binding energy of each major component and the target protein belongs.

[0073] Specifically, as shown in Table 2, the binding energy scoring criteria are as follows: when the binding energy is not greater than -10.0, the corresponding binding energy score is 5 points; when the binding energy is between -9.9 and -8.5, the corresponding binding energy score is 4 points; when the binding energy is between -8.4 and -7.0, the corresponding binding energy score is 3 points; when the binding energy is between -6.9 and -5.0, the corresponding binding energy score is 2 points; and when the binding energy is greater than -5.0, the corresponding binding energy score is 1 point. By calculating the binding energy values, the affinity and interaction strength between the main components in the raw material and the target protein are scientifically predicted and scored.

[0074] Table 2

[0075]

[0076]

[0077] The raw material quality analysis method based on multidimensional data fusion provided in this embodiment ensures the specificity of the assessment by matching target proteins with target functions. It calculates binding energy and determines scores based on molecular docking technology, breaking through the limitations of traditional single-index evaluation. It can accurately predict the affinity and interaction strength between components and targets, quantify the contribution weight of each component to efficacy, and comprehensively reveal the synergistic mechanism between components. It provides a scientific quantitative basis for raw material screening and formulation optimization, improves the accuracy and scientific nature of health food research and development, effectively avoids efficacy misjudgments caused by single indicators, and promotes the industry towards a data-driven precision research and development model.

[0078] Step S2022: The bioavailability and drug-likeness of each major component are retrieved through the Traditional Chinese Medicine System Pharmacology Database and Analysis Platform. The bioavailability score is obtained by scoring according to the corresponding bioavailability scoring standard, and the drug-likeness score is obtained by scoring according to the corresponding drug-likeness scoring standard.

[0079] Specifically, by querying online databases, such as the Traditional Chinese Medicine Systems Pharmacology (TCMSP) database, the bioavailability (OB value) and drug-likeness (DL value) parameters of each major component in the raw material extract are retrieved. A scientific scoring model is constructed, as shown in Tables 3 and 4, which are the bioavailability scoring criteria and drug-likeness scoring criteria, respectively. Based on the scores corresponding to different ranges in the scoring criteria, the bioavailability score and drug-likeness score of each major component in the target raw material extract are determined. For example, ginsenoside Rg1 has an OB value of 10.2%, and based on Table 3, its bioavailability score is determined to be "1"; its DL value is 0.78, and based on Table 4, its drug-likeness score is determined to be "4". Ginsenoside Rb1 has an OB value of 6.29%, and based on Table 3, its bioavailability score is determined to be "1"; its DL value is 0.04, and based on Table 4, its drug-likeness score is determined to be "1". This is just an example and is not a limitation.

[0080] Table 3

[0081] Bioavailability (OB value) score Absorption level ≥80％ 5 Excellent absorption 60-79％ 4 Good absorption 40-59％ 3 moderate absorption 20-39％ 2 Poor absorption <20％ 1 Difficult to absorb

[0082] Table 4

[0083] Drug-like properties (DL value) score rating level ≥0.8 5 Excellent drug-like properties 0.7≤DL<0.8 4 Good drug-like properties 0.5≤DL<0.7 3 moderate drug-like properties 0.3≤DL<0.5 2 Poor drug-like properties DL<0.3 1 Extremely poor drug-like properties

[0084] Step S2023: Retrieve literature based on the preset database, and score it according to whether there is literature record, whether there is in vivo experimental verification, and whether there is in vitro experimental verification to obtain the known literature verification score.

[0085] Specifically, authoritative academic databases such as CNKI, PubMed, and Web of Science were comprehensively utilized, employing a systematic keyword combination search strategy to obtain comprehensive and accurate domestic and international research literature on each component and the proposed health benefits. A quantitative scoring system based on research levels was constructed, grading and scoring different dimensions from basic research (e.g., cell and animal experiments), preclinical research to clinical research, combining factors such as evidence level, sample size, and experimental design rigor. Table 5 shows the scoring criteria validated based on known literature.

[0086] Table 5

[0087] Standard Description score There is publicly available in vivo experimental data to verify this. 2 There is publicly available in vitro experimental validation data. 1 No documented 0

[0088] Step S2024: Based on the binding energy score, bioavailability score, drug-likeness score, known literature verification score, and corresponding preset weights of each major component, the quality score of each major component is calculated using a weighted summation method.

[0089] Specifically, based on the binding energy score, bioavailability score, drug-likeness score, and known literature validation score of each major component obtained above, and combined with the weighting coefficients of each preset quality indicator in Table 1, the quality score of each major component is calculated using a weighted summation method. The calculation formula is as follows:

[0090] The quality score of the main component = (binding energy score × 0.4) + (bioavailability score × 0.30) + (drug-likeness score × 0.15) + (known literature verification score × 0.15).

[0091] In some optional implementations, step S2024 above includes:

[0092] Step b1 involves standardizing the binding energy score, bioavailability score, drug-likeness score, and known literature validation score to obtain multiple scores with the same scoring criteria.

[0093] Step b2: Based on multiple scores with the same scoring criteria and their corresponding preset weights, calculate the quality score of the main component using the weighted summation method.

[0094] Specifically, to avoid numerical deviations caused by differences in scoring ranges (e.g., binding energy scores of 1-5 points, literature verification scores of 0-2 points), the scoring ranges of each preset quality indicator can be unified, allowing scores from each dimension to directly participate in weighted calculations. For example, if the literature verification score (0-2 points) is unified to the same range (0-5) as the other indicators, the literature verification scoring criteria would be: 5 points for publicly published in vivo experimental verification data; 2.5 points for publicly published in vitro experimental verification data; and 0 points for no literature record. This is just an example and is not a limitation. By unifying the scoring ranges of each indicator, the contribution ratio of both to the activity of the component can be accurately reflected.

[0095] This embodiment provides a raw material quality analysis method based on multidimensional data fusion. This invention overcomes the limitations of traditional single-indicator evaluation by standardizing the scores of each dimension and combining them with weighted summation to calculate the quality score, achieving quantitative fusion of multidimensional data. This method eliminates dimensional differences between different scoring systems, making heterogeneous data such as binding energy and bioavailability comparable. Through weight allocation, it accurately reflects the contribution ratio of each indicator to the activity of the components. It can comprehensively reveal the synergistic effects between components, avoiding misjudgments of efficacy due to single-dimensional bias, and providing a scientific quantitative basis for raw material quality control and formulation optimization.

[0096] The raw material quality analysis method based on multidimensional data fusion provided in this embodiment deeply integrates four core information units: raw material component spectrum analysis, molecular simulation binding energy prediction, bioactivity characteristic parameters, and experimental literature evidence. By constructing a systematic quantitative model, it accurately calculates the contribution weight of each active ingredient in the raw material to the overall efficacy, comprehensively revealing the raw material quality characteristics, efficacy potential, and synergistic mechanism among components, and providing scientific guidance for raw material screening and formulation optimization.

[0097] Step S203 involves summing the quality scores of each major component to obtain the quality analysis results of the target raw material. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0098] The raw material quality analysis method based on multidimensional data fusion provided in this embodiment accurately quantifies the contribution of each major component to the overall efficacy of the raw material, determines the quality score of each major component in the target raw material, and forms a comprehensive raw material scoring system covering component activity, content distribution and clinical value through standardized calculation process. By integrating multidimensional data, it breaks through the limitations of traditional single indicators, accurately quantifies the contribution and synergistic effect of each component, and improves the accuracy of assessment by combining content and activity scores.

[0099] This embodiment provides a method for evaluating health food based on multidimensional data fusion, which can be used in the aforementioned computer system. Figure 3This is a flowchart of a health food evaluation method based on multidimensional data fusion according to an embodiment of the present invention, such as... Figure 3 As shown, the process includes the following steps:

[0100] Step S301: Obtain the target function of the target health food and screen efficacy target proteins based on the target function.

[0101] Specifically, taking the application of "antioxidant" function for health food products as an example, the target function is "antioxidant". The core mechanism of the antioxidant function is to scavenge free radicals (such as superoxide anion and hydroxyl radicals). It is necessary to screen key enzymes or proteins related to free radical scavenging as targets. Through TCMSP database and literature search, superoxide dismutase (SOD) was identified as the main target protein. It catalyzes the conversion of superoxide anion into oxygen and hydrogen peroxide in the antioxidant pathway.

[0102] Step S302: Obtain multiple test formulations of the target health food, determine multiple main raw materials and their corresponding content percentages in each test formulation, and determine the quality score of each main raw material according to the raw material quality analysis method based on multidimensional data fusion in any of the above embodiments.

[0103] Specifically, let's take two test formulations as examples. The first test formulation is a ginseng extract formulation, whose main raw materials and contents include: ginsenoside Rg1 content of 20%; ginsenoside Rb1 content of 15%. The calculation process for the raw material quality score (taking ginsenoside Rg1 as an example) includes:

[0104] (1) Molecular docking binding energy: The binding energy with SOD is -11.0 kcal / mol. According to Table 2, the binding energy score is 5 points.

[0105] (2) Bioavailability (OB value): 10.2%, determined according to Table 3, the bioavailability score is 1 point;

[0106] (3) Drug class (DL value): 0.78, determined according to Table 4, the drug class score is 4 points;

[0107] (4) Literature verification: There is in vitro antioxidant experimental data. According to Table 5, the score for known literature verification is 1 point.

[0108] (5) Weighted summation: The quality score of ginsenoside Rg1 is: 5×40%+1×30%+4×15%+1×15%=3.05 points.

[0109] The second tested formulation is a Panax notoginseng extract formulation, whose main raw materials and contents include: Panax notoginseng saponin R1 content of 18%; Ginsenoside Rg3 content of 12%. The calculation process for the raw material quality score (taking Panax notoginseng saponin R1 as an example) includes:

[0110] (1) Binding energy: -8.0 kcal / mol. According to Table 2, the binding energy score is 3 points.

[0111] (2) OB value: 5.43%, determined according to Table 3, bioavailability score is 1 point;

[0112] (3) DL value: 0.13, determined according to Table 4, the drug class score is 1 point;

[0113] (4) Literature verification: There is no clinical data. According to Table 5, the score for verification of known literature is 0.

[0114] (5) Weighted summation: The quality score of Panax notoginseng saponin R1 is: 3×40%+1×30%+1×15%+0×15%=1.65 points.

[0115] Step S303: Based on the quality scores and corresponding content percentages of the main raw materials in each test formulation, a coupled calculation is performed to obtain the comprehensive performance index of the test formulation.

[0116] Specifically, the comprehensive score of a single substance is coupled with its content ratio in the total raw materials for calculation. The Comprehensive Efficiency Index (CEI) is calculated using the formula: (CEI) = Σ[(Ci% × Si)], where Ci% represents the mass percentage of main component i (ΣCi% = 100%), and Si represents the baseline mass score of main component i. This accurately quantifies the actual contribution of each compound to the overall efficiency of the raw materials.

[0117] Based on the calculation results in step S302, calculate the comprehensive efficacy index of the first and second test formulations. First test formulation: Ginsenoside Rg1: 20% × 3.05 = 0.61; Ginsenoside Rb1: 15% × 3.8 (assuming a quality score of 3.8) = 0.57; CEI = 0.61 + 0.57 = 1.18. Second test formulation: Panax notoginseng saponin R1: 18% × 1.65 = 0.297; Ginsenoside Rg3: 12% × 3.5 (assuming a quality score of 3.5) = 0.42; CEI = 0.297 + 0.42 = 0.717.

[0118] In some optional implementations, after determining the overall efficacy index of the formulation to be tested, the method further includes:

[0119] Based on the target function, the formulation with the best overall performance is selected from all the formulations under test according to the summative efficacy index of each formulation.

[0120] Specifically, an additive algorithm was used to rank the overall efficacy of all compounds. Combining the proposed health benefits and R&D goals of the product, data comparison and priority ranking algorithms were employed to select the optimal combination and ratio of raw materials with the best overall score and synergistic effect from the candidate raw material library and formulation schemes.

[0121] Comparing the comprehensive efficacy index of the first and second test formulations, the comprehensive efficacy index of the first test formulation is higher, and its main components have stronger binding energy with ginsenosides and SOD, and better bioavailability. Therefore, the ginseng extract formulation was selected as the optimal formulation for antioxidant function. This is only an example and is not a limitation.

[0122] The health food evaluation method based on multidimensional data fusion provided in this embodiment breaks through the limitations of single-indicator evaluation models by integrating multidimensional data. It achieves a scientific and quantitative evaluation of the entire chain from raw material screening to formulation optimization. Based on the target function, it accurately matches target proteins to ensure the targeting of the evaluation. By combining the raw material quality score and content ratio for coupled calculation, it quantifies the synergistic effect of multiple components. By integrating multi-dimensional data such as component activity, content distribution, and clinical evidence, it forms a comprehensive evaluation system covering the quality and efficacy potential of raw materials. This provides a data-driven decision-making basis for formulation optimization, effectively improving the accuracy and scientific nature of health food research and development, and promoting the industry's upgrade to an intelligent evaluation model based on multidimensional data fusion.

[0123] This embodiment also provides a raw material quality analysis device based on multidimensional data fusion. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0124] This embodiment provides a raw material quality analysis device based on multi-dimensional data fusion, such as... Figure 4 As shown, it includes:

[0125] The component analysis module 401 is used to perform component analysis on the extract of the target raw material to determine the multiple main components contained in the target raw material.

[0126] The main component scoring module 402 is used to perform quality analysis on each main component according to preset quality indicators and obtain the quality score of each main component.

[0127] The raw material quality analysis module 403 is used to sum the quality scores of each major component to obtain the quality analysis results of the target raw material.

[0128] In some alternative implementations, the principal component scoring module 402 includes:

[0129] The binding energy scoring unit is used to calculate the binding energy between each major component and the target protein based on molecular docking technology, and to determine the binding energy score corresponding to the binding energy value according to the binding energy scoring standard.

[0130] The pharmacological scoring unit is used to retrieve the bioavailability and drug-likeness of each major component through the pharmacological database and analysis platform of traditional Chinese medicine, and to score them according to the corresponding bioavailability scoring standard to obtain a bioavailability score and according to the corresponding drug-likeness scoring standard to obtain a drug-likeness score.

[0131] The literature verification scoring unit is used to retrieve literature based on a preset database and score it according to whether it is documented in literature, whether there is in vivo experimental verification, or whether there is in vitro experimental verification, to obtain a known literature verification score.

[0132] The weighted summation scoring unit is used to calculate the quality score of each major component based on the binding energy score, bioavailability score, drug-likeness score, known literature verification score, and corresponding preset weights, using a weighted summation method.

[0133] This embodiment also provides a health food evaluation device based on multi-dimensional data fusion, such as... Figure 5 As shown, the device includes:

[0134] The target protein identification module 501 is used to obtain the target function of the target health food and screen efficacy target proteins based on the target function.

[0135] The raw material scoring module 502 is used to perform principal component analysis on the target health food, determine the multiple main raw materials that make up the target health food and their corresponding content proportions, and determine the quality score of each main raw material according to the raw material quality analysis method based on multidimensional data fusion in any of the above embodiments.

[0136] The functional evaluation module 503 is used to perform coupled calculations based on the quality scores and corresponding content ratios of each main raw material to obtain the comprehensive efficacy index of the target health food. The comprehensive efficacy index is used to evaluate the function of the health food.

[0137] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0138] In this embodiment, the raw material quality analysis device and the health food evaluation device based on multidimensional data fusion are presented in the form of functional units. Here, a unit refers to an ASIC (Application Specific Integrated Circuit), a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0139] This invention also provides a computer device having the above-described features. Figure 4 The raw material quality analysis device shown is based on multidimensional data fusion. Figure 5 The device shown is a health food evaluation device based on multidimensional data fusion.

[0140] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6 As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0141] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0142] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0143] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0144] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0145] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0146] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0147] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A raw material quality analysis method based on multidimensional data fusion, characterized in that, The method includes: Component analysis was performed on the extract of the target raw material to identify several major components contained in the target raw material; According to the preset quality indicators, the quality of each major component is analyzed to obtain the quality score of each major component; The quality analysis results of the target raw material are obtained by summing the quality scores of each major component.

2. The method according to claim 1, characterized in that, The preset quality indicators include: molecular docking binding energy, bioavailability, drug-likeness, and verification from known literature. Based on these preset quality indicators, quality analysis is performed on each major component to obtain a quality score for each major component, including: The binding energy of each major component to the target protein is calculated based on molecular docking technology, and the binding energy score corresponding to the binding energy value is determined according to the binding energy scoring standard. The bioavailability and drug-likeness of each major component were retrieved through the pharmacology database and analysis platform of traditional Chinese medicine. The bioavailability score was obtained by scoring according to the corresponding bioavailability scoring standard, and the drug-likeness score was obtained by scoring according to the corresponding drug-likeness scoring standard. Based on literature retrieval from a pre-defined database, scores are assigned according to whether there is literature record, whether there is in vivo experimental verification, and whether there is in vitro experimental verification, to obtain a known literature verification score. The quality score of each major component is calculated using a weighted summation method based on its binding energy score, bioavailability score, drug-likeness score, known literature validation score, and corresponding preset weights.

3. The method according to claim 2, characterized in that, The method involves calculating the binding energy between each major component and the target protein based on molecular docking technology, and determining the binding energy score corresponding to the binding energy value according to the binding energy scoring standard, including: The functions of the target product are obtained, and multiple functional target proteins are selected as target target proteins based on the functions of the target product. Using molecular docking software, each major component was docked with the target protein one by one to obtain the binding energy between each major component and the target protein. Based on the scoring criteria, the range of binding energy values ​​corresponding to different scores is determined. According to the range of binding energy values ​​to which the binding energy of each major component belongs to the target protein, the binding energy score of each major component is determined.

4. The method according to claim 2, characterized in that, Based on the binding energy score, bioavailability score, drug-likeness score, known literature validation score, and corresponding preset weights of each major component, a weighted summation method was used to calculate the quality score of each major component, including: The binding energy score, bioavailability score, drug-likeness score, and known literature validation score were standardized to obtain multiple scores with the same scoring criteria. The quality score of the main component is calculated by using a weighted summation method based on multiple scores with the same scoring criteria and their corresponding preset weights.

5. A method for evaluating health food based on multidimensional data fusion, characterized in that, The method includes: Obtain the target function of the target health food, and screen efficacy target proteins based on the target function; Obtain multiple test formulations of the target health food, determine multiple main raw materials and their corresponding content ratios in each test formulation, and determine the quality score of each main raw material according to the raw material quality analysis method based on multidimensional data fusion as described in any one of claims 1-4. The comprehensive efficacy index of the test formulation is obtained by coupling calculation based on the quality score and corresponding content ratio of the main raw materials in each test formulation.

6. The method according to claim 5, characterized in that, The method further includes: Based on the target function, the formulation with the best overall performance is selected from all the formulations under test according to the summative efficacy index of each formulation.

7. A raw material quality analysis device based on multidimensional data fusion, characterized in that, The device includes: The component analysis module is used to perform component analysis on the extract of the target raw material to determine the multiple main components contained in the target raw material; The main component scoring module is used to perform quality analysis on each main component according to preset quality indicators and obtain the quality score of each main component. The raw material quality analysis module is used to sum the quality scores of each major component to obtain the quality analysis results of the target raw material.

8. A health food evaluation device based on multidimensional data fusion, characterized in that, The device includes: The target protein identification module is used to obtain the target function of the target health food and screen efficacy target proteins according to the target function. The raw material scoring module is used to perform principal component analysis on the target health food, determine the multiple main raw materials that make up the target health food and their corresponding content proportions, and determine the quality score of each main raw material according to the raw material quality analysis method based on multidimensional data fusion according to any one of claims 1-4. The functional evaluation module is used to perform coupled calculations based on the quality scores and corresponding content percentages of each main raw material to obtain the comprehensive efficacy index of the target health food. The comprehensive efficacy index is used to evaluate the function of the health food.

9. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the raw material quality analysis method based on multidimensional data fusion as described in any one of claims 1 to 4, or the health food evaluation method based on multidimensional data fusion as described in any one of claims 5 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the raw material quality analysis method based on multidimensional data fusion as described in any one of claims 1 to 4, or the health food evaluation method based on multidimensional data fusion as described in any one of claims 5 to 6.

Images